Search

As the power density of modern CPUs is gradually increasing, thermal management has become one of the primary concerns for multicore systems, where task scheduling and dynamic voltage/frequency scaling (DVFS) play a pivotal role in effectively managing the system temperature. In this paper, we propose CARTAD, a new reinforcement learning (RL) based task scheduling and DVFS method for temperature minimization and latency guarantee on multicore systems. The novelty of CARTAD framework is that we exploit machine learning technique to analyze the applications’ intermediate representations (IRs) generated by compiler and identify an important feature which is critical for predicting the application’s performance. With the newly explored feature, we construct a RL-based scheduler with the more effective state representation and reward function such that the system temperature can be minimized while guaranteeing applications’ latency. We implement and evaluate CARTAD on real platforms in comparison with the stateof-the-art approaches. Experimental results show CARTAD can reduce the maximum temperature by up to 16∘C and the average temperature by up to 10∘C.

Hardware systems integrated with deep neural networks (DNNs) are deemed to pave the way for future artificial intelligence (AI). However, manually designing efficient DNNs involves non-trivial computation resources since significant trial-and-errors are required to finalize the network configuration. To this end, we, in this paper, introduce a novel hardware-aware neural architecture search (NAS) framework, namely GoldenNAS, to automate the design of efficient DNNs. To begin with, we present a novel technique, called dynamic channel scaling, to enable the channel-level search since the number of channels has non-negligible impacts on both accuracy and efficiency. Besides, we introduce an efficient progressive space shrinking method to raise the awareness of the search space towards target hardware and alleviate the search overheads as well. Moreover, we propose an effective hardware performance modeling method to approximate the runtime latency of DNNs upon target hardware, which is further integrated into GoldenNAS to avoid the tedious on-device measurements. Then, we employ the evolutionary algorithm (EA) to search for the optimal operator/channel configurations of DNNs, denoted as GoldenNets. Finally, to enable the depthwise adaptiveness of GoldenNets under dynamic environments, we propose the adaptive batch normalization (ABN) technique, followed by the self-knowledge distillation (SKD) approach to improve the accuracy of adaptive sub-networks. We conduct extensive experiments directly on ImageNet, which clearly demonstrate the advantages of GoldenNAS over existing state-of-the-art approaches. Ministry of Education (MOE) Nanyang Technological University Submitted/Accepted version This work is partially supported by the Ministry of Education, Singapore, under its Academic Research Fund Tier 2 (MOE2019-T2-1-071) and Tier 1 (MOE2019-T1-001-072), and partially supported by Nanyang Technological University, Singapore, under its NAP (M4082282) and SUG (M4082087).

SMART NoC, which transmits unconflicted flits to distant processing elements (PEs) in one cycle through the express bypass, is a high-performance NoC design proposed recently. However, if contention occurs, flits with low priority would not only be buffered but also could not fully utilize bypass. Although there exist several routing algorithms that decrease contentions by rounding busy routers and links, they cannot be directly applicable to SMART since it lacks the support for arbitrary-turn (i.e. the number and direction of turns are free of constraints) routing. Thus, in this article, to minimize contentions and further utilize bypass, we propose an improved SMART NoC, called ArSMART, in which arbitrary-turn transmission is enabled. Specifically, ArSMART divides the whole NoC into multiple clusters where the route computation is conducted by the cluster controller and the data forwarding is performed by the bufferless reconfigurable router. Since the long-range transmission in SMART NoC needs to bypass the intermediate arbitration, to enable this feature, we directly configure the input and output ports connection rather than apply hop-by-hop table-based arbitration. To further explore the higher communication capabilities, effective adaptive routing algorithms that are compatible with ArSMART are proposed. The route computation overhead, one of the main concerns for adaptive routing algorithms, is hidden by our carefully designed control mechanism. Compared with the state-of-the-art SMART NoC, the experimental results demonstrate an average reduction of 40.7% in application schedule length and 29.7% in energy consumption. Ministry of Education (MOE) Nanyang Technological University This work is partially supported by the Ministry of Education, Singapore, under its Academic Research Fund Tier 2 (MoE2019-T2-1-071) and Tier 1 (MoE2019-T1-001-072), and Nanyang Technological University, Singapore, under its NAP (M4082282) and SUG (M4082087).

Edge computing and artificial intelligence (AI), especially deep learning for nowadays, are gradually intersecting to build a novel system, called edge intelligence. However, the development of edge intelligence systems encounters some challenges, and one of these challenges is the \textit{computational gap} between computation-intensive deep learning algorithms and less-capable edge systems. Due to the computational gap, many edge intelligence systems cannot meet the expected performance requirements. To bridge the gap, a plethora of deep learning techniques and optimization methods are proposed in the past years: light-weight deep learning models, network compression, and efficient neural architecture search. Although some reviews or surveys have partially covered this large body of literature, we lack a systematic and comprehensive review to discuss all aspects of these deep learning techniques which are critical for edge intelligence implementation. As various and diverse methods which are applicable to edge systems are proposed intensively, a holistic review would enable edge computing engineers and community to know the state-of-the-art deep learning techniques which are instrumental for edge intelligence and to facilitate the development of edge intelligence systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search and adaptive deep learning models. Finally, based on observations and simple experiments we conducted, we discuss some future directions. Submitted/Accepted version

Objective: Despite studies reporting alterations in the brain networks of patients with ADHD, alterations in the modularity of white matter (WM) networks are still unclear. Method: Based on the results of module division by generalized Louvain algorithm, the modularity of ADHD was evaluated. The correlation between the modular changes of ADHD and its clinical characteristics was analyzed. Results: The participation coefficient and the connectivity between modules of ADHD increased, and the modularity coefficient decreased. Provincial hubs of ADHD did not change, and the number of connector hubs increased. All results showed that the modular segregation of WM networks of ADHD decreased. Modules with reduced modular segregation are mainly responsible for language and motor functions. Moreover, modularity showed evident correlation with the symptoms of ADHD. Conclusion: The modularity changes in WM network provided a novel insight into the understanding of brain cognitive alterations in ADHD.

In this paper, we propose O-Star, a scalable optical switching architecture for on-chip many-core systems, employing hybrid mode and wavelength division multiplexing technology. The O-Star uses the Benes topology as the core switching module to realize non-blocking switching. Besides, we design a wavelength and mode allocation module to enable each processor to transmit data in parallel. To quantitatively analyze the minimum hardware cost required, we establish a mathematical model for the different number of processors. As a proof of concept, a 64-core optical switching architecture featuring 8-port Benes topology, 2-mode, and 4-wavelength channels is simulated with single channel 25 Gbps data rate. The O-Star is flexible to scale, both for the number of supported processors and the switching capacity. O-Star holds promise for realizing large-scale optical switching networks to address the incoming challenges of high-performance computing (HPC) systems and data center networks (DCNs).

The Tibetan Plateau (TP) is one of the most climate sensitive regions around the world. Aerosols imported from adjacent regions reach its peak during the pre-monsoon season and play a vital role in the TP environment. However, the strong interannual variation in aerosols transported to the TP has not been fully understood. Here, we show that the interannual variability of pre-monsoon aerosols transported to the TP is influenced more by rainfall over the southern Himalayas than near-surface wind. Rainfall modulates fire events and biomass burning emissions and reduces aerosols over the TP by wet scavenging. Contrary to the role of wind in increasing aerosol transport, the positive correlation between wind and aerosols in the TP reported in previous studies is contributed by the negative interannual correlations between wind and rainfall and between rainfall and fire events over the southern Himalayas. This study highlights the co-variability of wind and rainfall and their confounding impacts on aerosols in the southern Himalayas and over the TP. With pre-monsoon rainfall projected to increase in adjacent regions of southern TP, aerosol transport to the TP may be mitigated in the future.

Heterogeneous computing systems (HCSs), which consist of various processing elements (PEs) that vary in their processing ability, are usually facilitated by the network-on-chip (NoC) to interconnect its components. The emerging point-to-point NoCs which support single-cycle-multi-hop transmission, reduce or eliminate the latency dependence on distance, addressing the scalability concern raised by high latency for long-distance transmission and enlarging the design space of the routing algorithm to search the non-shortest paths. For such point-to-point NoC-based HCSs, resource management strategies which are managed by compilers, scheduler, or controllers, e.g., mapping and routing, are complicated for the following reasons: (i) Due to the heterogeneity, mapping and routing need to optimize computation and communication concurrently (for homogeneous computing systems, only communication). (ii) Conducting mapping and routing consecutively cannot minimize the schedule length in most cases since the PEs with high processing ability may locate in the crowded area and suffer from high resource contention overhead. (iii) Since changing the mapping selection of one task will reconstruct the whole routing design space, the exploration of mapping and routing design space is challenging. Therefore, in this work, we propose MARCO, the m apping a nd r outing co -optimization framework, to decrease the schedule length of applications on point-to-point NoC-based HCSs. Specifically, we revise the tabu search to explore the design space and evaluate the quality of mapping and routing. The advanced reinforcement learning (RL)algorithm, i.e., advantage actor-critic, is adopted to efficiently compute paths. We perform extensive experiments on various real applications, which demonstrates that the MARCO achieves a remarkable performance improvement in terms of schedule length (+44.94% ∼ +50.18%) when compared with the state-of-the-art mapping and routing co-optimization algorithm for homogeneous computing systems. We also compare MARCO with different combinations of state-of-the-art mapping and routing approaches.

Background: To understand the status of cancer patients’ awareness and demand for remote palliative care service and to provide a reference for promoting the formulation of remote palliative care policy.Methods: A small across-section design involved a sample of 148 cancer adults in the First Affiliated Hospital of Guangxi Medical University, who were conducted by self-designed questionnaire via the Questionnaire Star. The questionnaire contained basic information (14 items) and the attitude towards the remote palliative care (6 items).Results: The rate of patients who supported to take remote palliative care was 41.2%. It related with age, education level, occupation, family income, insurance type, self-care ability, smartphone and communication app using, and the using time(p＜0.05). Most of them hoped to get remote palliative care 24 hours. Almost half of the patients would like to be charged by items and they hoped the price of remote palliative care be cheap. Most of the patients didn’t really care about the working years and title of the care provider, but half of them more believed Grade 3, Class A hospital. The top three demand of remote palliative care were pain reducing, nutrition counseling, and nursing instruction.Conclusion: Remote palliative care has a good application prospect for cancer patients, but there are still some challenges, which need further exploration and development, including appropriate infrastructure, reasonable price and sufficient personnel to provide remote palliative care services.

The coronavirus disease 2019 (COVID-19) has spread worldwide in unprecedented speed, and diverse negative impacts have seriously endangered human society. Accurately forecasting the number of COVID-19 cases can help governments and public health organizations develop the right prevention strategies in advance to contain outbreaks. In this work, a long-term 6-month COVID-19 pandemic forecast in second half of 2021 and a short-term 30-day daily ahead COVID-19 forecast in December 2021 are successfully implemented via a novel nanophotonic reservoir computing based on silicon optomechanical oscillators with photonic crystal cavities, benefitting from its simpler learning algorithm, abundant nonlinear characteristics, and some unique advantages such as CMOS compatibility, fabrication cost, and monolithic integration. In essence, the nonlinear time series related to COVID-19 are mapped to the high-dimensional nonlinear space by the optical nonlinear properties of nanophotonic reservoir computing. The testing-dataset forecast results of new cases, new deaths, cumulative cases, and cumulative deaths for six countries demonstrate that the forecasted blue curves are awfully close to the real red curves with exceedingly small forecast errors. Moreover, the forecast results commendably reflect the variations of the actual case data, revealing the different epidemic transmission laws in developed and developing countries. More importantly, the daily ahead forecast results during December 2021 of four kinds of cases for six countries illustrate that the daily forecasted values are highly coincident with the real values, while the relevant forecast errors are tiny enough to verify the good forecasting competence of COVID-19 pandemic dominated by Omicron strain. Therefore, the implemented nanophotonic reservoir computing can provide some foreknowledge on prevention strategy and healthcare management for COVID-19 pandemic.